© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26296
    Prev
    Next
    INDEX
    Explanations

    the word "this" with high repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    342
    +0.12
    0.7%
    133
    +0.12
    0.7%
    301
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.12
    0.16
    26
    +0.12
    0.14
    199
    +0.10
    0.14
    Negative Logits
    ries
    -1.67
    respectively
    -1.62
    icia
    -1.61
     object
    -1.56
    ardo
    -1.48
     com
    -1.47
    com
    -1.46
    ice
    -1.46
     origin
    -1.45
    ury
    -1.41
    POSITIVE LOGITS
    Ĥ¬
    5.02
    Īĺ
    4.63
    ĻĤ
    4.50
    ĥ½
    4.42
    Ļª
    4.33
    ĩ
    4.33
       ↵
    4.32
    4.32
    4.32
    4.31
    Activations Density 0.277%

    No Known Activations